Okingjo's Multi-identifier LORAs

I will share most of my LORA model with multiple identifier here. by saying "multiple", one charater with two or more costumes are stored within the model. Not only will the LORA model will be post here, training setups and tips will also be shared. I`m still in the state of learning, so any comments/feedbacks are welcom!

some tips during trainig

general idea

The way to have multiple identifiers within one Lora is by using captioning. Since most auto captioning of an anime character starts with "1girl/boy", the second prompt will be used as the triggering word, i.e. the prompt to let the AI to excite the desired costume. Captioning the images properly and put them into different folders respectively, just as the Kohya_SS SD trainier docs says, and you are good to go.

captioning tips

Automatic captioning with manual tweak, minimizing the overlap between each identifier.

Charater from Genshin

Ningguang/凝光

Brief intro

LORA of Ningguang, with two costumes in game. civitAI page Download

Training dataset

Default costume

72 images in total, in folder "30_Ningguang"

36 normal illustrations
15 normal 360 3D model snapshots
5 nude illustrations
16 nude 360 3D model snapshots

Orchid costume

43 images in total, in folder "20_NingguangOrchid"

11 normal illustrations
15 normal 360 3D model snapshots
2 nude illustrations
15 nude 360 3D model snapshots

Captioning

WD14 captioning instead of the deepdanbooru caption was used, since the former one will not crop/resize the images. Threshold are usually set to 0.75-0.8. since I don't like to have a very long and sometimes inaccurate caption for my training data. After captionin is done, I added "ningguang \ (genshin impact\ )" after "1girl" to every caption file of the default costume, and "ningguang \ (orchid's evening gown\ ) \ (genshin impact\ )" to the orchid costume. Some of the caption files were empty so I have to manually type the words.

Training setup

Trained with Kohya_SS stable diffusion trainer Base model was Anything V3.0 full Trainig process consist of two phases. The first one with default parameters of:

learning_rate: 0.0001
text_encoder_lr: 5e-5
unet_lr: 0.0001 and 6 epoch, After phase 1, choose the one with the best result (a little bit underfitting, no over fitting, and the two costume are seperated), which is the 6th one. Then trained with 1/10 of the original LR for another 7 epochs.

Result

Barbara/芭芭拉

Brief intro

LORA of Barbara, with two costumes in game. The filesize of the model has been decreased to 1/4, i.e. 2 identifiers in a 64 size (was 1 identifier per 128). On one hand, saving storasge; on the other hand, fewer room for char with lower priority. in summary, less is better!

Training dataset

Default costume

164 images in total, in folder "10_barbara_(genshin_impact) 1girl"

104 illustrations, bothSFW and NSFW, handpicked to ensure best quality
30 normal 360 3D model snapshots
30 nude 360 3D model snapshots

Summertime swimsuit

94 imges in total, in folder "16_barbara_(summertime_sparkle)_(genshin_impact) 1girl"

64 illustrations, bothSFW and NSFW, handpicked to ensure best quality
30 normal 360 3D model snapshots

Captioning

It was the first time that the standard Danbooru style prompt was used for captioning. "barbara_(genshin_impact)" and "barbara_(summertime_sparkle)_(genshin_impact)" were added to each costume respectively.

Training setup

Defalut LR fo 4 epochs, then 1/10 default LR for another 8 epochs. Trainig basing on anything v3. Total steps is: (4+8)x(164x10+94x16)=37,728

results

Charater from Honkai impact

Elysia/爱莉希雅-V2

Brief intro

LORA of Elysia, with 5 costumes in game. civitAI page Download

Training dataset

Default costume/Miss Pink Elf

75 images in total, in folder "14_Elysia (miss pink elf) 1girl"

45 normal illustrations, non-nude
30 normal 360 3D model snapshots

Default herrscher costume/herrscher of human:ego

129 images in total, in folder "11_elysia (herrscher of humanego) 1girl"

39 normal illustrations, included few NSFW, not completely nude though
90 normal 360 3D model snapshots

Miad costume

75 images in total, in folder “16_Elysia-maid 1girl”

45 normal illustrations, non-nude
30 normal 360 3D model snapshots

swimsuit

80 images in total, in folder “14_elysia-swimsuit 1girl”

20 normal illustrations, non-nude
60 normal 360 3D model snapshots In addition, I have also included 52 images with non-official costumes in a new folder "10_Elysia 1girl"

Captioning

Captioning with WD1.4, with threshold 0.7. After the auto captionin is done, I added "elysia \ (miss pink elf\ ) \ (honkai impact\ )", "elysia \ (herrscher of human:ego\ ) \ (honkai impact\ )", "Elysia-maid", "Elysia-swimsuit" and "1girl, elysia \ (honkai impact\ )" to the captioning respectively as identifiers. In addition, I also manually editted the captioning to make sure that there was no overlap of prompts between each concepts.

Training setup

Trained with Kohya_SS stable diffusion trainer Base model was Anything V3.0 full Trainig process consist of two phases. The first one with default parameters of:

Lion, Cosine with restarts
learning_rate: 0.00003
text_encoder_lr: 15e-6
unet_lr: 0.00003 Trained for 10 epochs with upper parameters, feel underfit, thus trained another 2 epoch with 1/3 the initial LR.